mlsanityData to 7 Oct 2026

Universal Adversarial Examples in Remote Sensing: Methodology and Benchmark

arXiv 2202.07054 ↗First posted 14 Feb 2022cs.CVcited by 24

Not on the map. Why?

Abstract (arXiv)

Deep neural networks have achieved great success in many important remote sensing tasks. Nevertheless, their vulnerability to adversarial examples should not be neglected. In this study, we systematically analyze the universal adversarial examples in remote sensing data for the first time, without any knowledge from the victim model. Specifically, we propose a novel black-box adversarial attack method, namely Mixup-Attack, and its simple variant Mixcut-Attack, for remote sensing data. The key idea of the proposed methods is to find common vulnerabilities among different networks by attacking the features in the shallow layer of a given surrogate model. Despite their simplicity, the proposed methods can generate transferable adversarial examples that deceive most of the state-of-the-art deep neural networks in both scene classification and semantic segmentation tasks with high success rates. We further provide the generated universal adversarial examples in the dataset named UAE-RS, which is the first dataset that provides black-box adversarial samples in the remote sensing field. We hope UAE-RS may serve as a benchmark that helps researchers to design deep neural networks with strong resistance toward adversarial attacks in the remote sensing field. Codes and the UAE-RS dataset are available online (https://github.com/YonghaoXu/UAE-RS).

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 50 of its 67 references that are in the map. First posted on arXiv 14 Feb 2022.

Builds on

50 of 67 references.

References · 50

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2016Densely Connected Convolutional Networkscited by 6,691
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  8. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  9. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  10. 2013Intriguing properties of neural networkscited by 5,114
  11. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  12. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
38 more
  1. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  3. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  4. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  5. 2016Pyramid Scene Parsing Networkcited by 2,472
  6. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  7. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  8. 2020Designing Network Design Spacescited by 954
  9. 2016Adversarial Machine Learning at Scalecited by 934
  10. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  11. 2017Remote Sensing Image Scene Classification: Benchmark and State of the Artcited by 791
  12. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  13. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 352
  14. 2016AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classificationcited by 343
  15. 2015Understanding Neural Networks Through Deep Visualizationcited by 332
  16. 2017ICNet for Real-Time Semantic Segmentation on High-Resolution Imagescited by 261
  17. 2019Simple Black-box Adversarial Attackscited by 249
  18. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
  19. 2017LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentationcited by 212
  20. 2019AdvHat: Real-world adversarial attack on ArcFace Face ID systemcited by 161
  21. 2019Enhancing Adversarial Example Transferability with an Intermediate Level Attackcited by 139
  22. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  23. 2016Full-Resolution Residual Networks for Semantic Segmentation in Street Scenescited by 71
  24. 2018Learning Transferable Adversarial Examples via Ghost Networkscited by 69
  25. 2020Universal Adversarial Attack on Attention and the Resulting Dataset DAmageNetcited by 45
  26. 2022Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domainscited by 42
  27. 2019Query-efficient Meta Attack to Deep Neural Networkscited by 33
  28. 2021Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attackscited by 33
  29. 2021Deep Learning for UAV-based Object Detection and Tracking: A Surveycited by 33
  30. 2018ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-timecited by 31
  31. 2021Semantic Segmentation of Remote Sensing Images with Sparse Annotationscited by 30
  32. 2018Adversarial Examples in Remote Sensingcited by 19
  33. 2019Yet another but more efficient black-box adversarial attack: tiling and evolution strategiescited by 17
  34. 2022Query Efficient Decision Based Sparse Attacks Against Black-Box Deep Learning Modelscited by 13
  35. 2018Multisource and Multitemporal Data Fusion in Remote Sensingcited by 8
  36. 2019Adversarial Example in Remote Sensing Image Recognitioncited by 8
  37. 2020Domain Adaptive Transfer Attack (DATA)-based Segmentation Networks for Building Extraction from Aerial Imagescited by 2
  38. 2021Demotivate adversarial defense in remote sensingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 4; 2024: 4; 2025: 5; 2026: 5.

24 papers.

Sort:

By area:

  1. 2024On the Foundations of Earth and Climate Foundation Modelscited by 31
  2. 2022Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networkscited by 28
  3. 2023RSDiff: Remote Sensing Image Generation from Text Using Diffusion Modelcited by 28
  4. 2022AI Security for Geoscience and Remote Sensing: Challenges and Future Trendscited by 23
  5. 2022Benchmarking Adversarial Patch Against Aerial Detectioncited by 21
  6. 2022Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and Defensecited by 14
  7. 2023CBA: Contextual Background Attack against Optical Aerial Detection in the Physical Worldcited by 7
  8. 2022Backdoor Attacks for Remote Sensing Data with Wavelet Transformcited by 6
  9. 2023A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarkingcited by 5
  10. 2023Universal Adversarial Defense in Remote Sensing Based on Pre-trained Denoising Diffusion Modelscited by 5
  11. 2025Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attackscited by 5
  12. 2024Responsible AI for Earth Observationcited by 4
12 more
  1. 2024Cloud Adversarial Example Generation for Remote Sensing Image Classificationcited by 2
  2. 2022Universal adversarial perturbation for remote sensing imagescited by 1
  3. 2024Towards Assessing the Synthetic-to-Measured Adversarial Vulnerability of SAR ATRcited by 1
  4. 2025On the Adversarial Vulnerabilities of Transfer Learning in Remote Sensingcited by 1
  5. 2025Generating Transferrable Adversarial Examples via Local Mixing and Logits Optimization for Remote Sensing Object Recognitioncited by 1
  6. 2026Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classificationcited by 1
  7. 2025Boosting Adversarial Transferability for Hyperspectral Image Classification Using 3D Structure-invariant Transformation and Weighted Intermediate Feature Divergencecited by 0
  8. 2025Revisiting Adversarial Training under Hyperspectral Imagecited by 0
  9. 2026AirflowAttack: Thermal-Airflow Adversarial Perturbations against Infrared Remote-Sensing Vision-Language Modelscited by 0
  10. 2026ColorFD: A Finite-Difference Guided Black-Box Physical Adversarial Attack for Remote Sensing Object Detectioncited by 0
  11. 2026On the Adversarial Robustness of Remote Sensing Semantic Change Detectioncited by 0
  12. 2026Printability-Constrained Adversarial Decals for Near-Nadir Aerial Perception: Measured Ink Gamuts, Nested Realism Constraints, and a Physical-World Boundcited by 0